Nicholas Carlini
Source-listed: Research Scientist · Anthropic
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Towards Evaluating the Robustness of Neural NetworksSaved credit: First author · 2017Explore people connected to this work →
- On Evaluating Adversarial RobustnessSaved credit: Contributor · 2019Explore people connected to this work →
- Scalable Extraction of Training Data from (Production) Language ModelsSaved credit: Contributor · 2023Explore byline and saved connections →
- Stealing Part of a Production Language ModelSaved credit: First author · 2024Explore people connected to this work →
- Evaluating and mitigating the growing risk of LLM-discovered 0-daysSaved credit: Contributor · 2026Explore people connected to this work →